Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.9476. Min Act: -0.1700
Data Index: 6185319 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.8226. Min Act: -0.1700
Data Index: 4837754 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.7289. Min Act: -0.1700
Data Index: 4675491 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.7289. Min Act: -0.1700
Data Index: 2207049 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.7289. Min Act: -0.1700
Data Index: 4365358 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6976. Min Act: -0.1700
Data Index: 7000407 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6976. Min Act: -0.1700
Data Index: 2890608 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6664. Min Act: -0.1700
Data Index: 4196211 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6664. Min Act: -0.1700
Data Index: 8618246 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6976. Min Act: -0.1700
Data Index: 8078720 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6351. Min Act: -0.1700
Data Index: 8485804 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6039. Min Act: -0.1700
Data Index: 1015613 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.6039. Min Act: -0.1700
Data Index: 3475107 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5726. Min Act: -0.1700
Data Index: 6639898 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5726. Min Act: -0.1700
Data Index: 6761999 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5726. Min Act: -0.1700
Data Index: 7721634 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5414. Min Act: -0.1700
Data Index: 6479765 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5414. Min Act: -0.1700
Data Index: 5150676 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5414. Min Act: -0.1700
Data Index: 1886800 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9476. Min Range: -4.9476
Max Act: 4.5101. Min Act: -0.1700
Data Index: 258023 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19